© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96126
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     than
    -1.00
     THAN
    -0.87
     niż
    -0.80
    Than
    -0.78
     kuin
    -0.75
    than
    -0.71
     Than
    -0.69
     än
    -0.69
    THAN
    -0.66
     ComVisible
    -0.62
    POSITIVE LOGITS
     disambiguazione
    0.73
     comparison
    0.69
     general
    0.68
     proportion
    0.65
     Allociné
    0.59
    proof
    0.56
     practice
    0.56
     général
    0.54
     незавершена
    0.53
    general
    0.52
    Activations Density 0.004%

    No Known Activations